Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1629 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7644. Min Range: -8.7644
Max Act: 8.7644. Min Act: -0.1700
Data Index: 7093188 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7644. Min Range: -8.7644
Max Act: 8.3894. Min Act: -0.1700
Data Index: 8609666 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7644. Min Range: -8.7644
Max Act: 8.2019. Min Act: -0.1700
Data Index: 5834350 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7644. Min Range: -8.7644
Max Act: 8.2644. Min Act: -0.1700
Data Index: 5911684 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7644. Min Range: -8.7644
Max Act: 8.2644. Min Act: -0.1700
Data Index: 547392 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7644. Min Range: -8.7644
Max Act: 8.2644. Min Act: -0.1700
Data Index: 4692423 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7644. Min Range: -8.7644
Max Act: 8.2019. Min Act: -0.1700
Data Index: 4542057 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7644. Min Range: -8.7644
Max Act: 8.1394. Min Act: -0.1700
Data Index: 5413582 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7644. Min Range: -8.7644
Max Act: 8.1082. Min Act: -0.1700
Data Index: 5372596 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7644. Min Range: -8.7644
Max Act: 8.0769. Min Act: -0.1699
Data Index: 2011677 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7644. Min Range: -8.7644
Max Act: 7.9832. Min Act: -0.1700
Data Index: 6171488 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7644. Min Range: -8.7644
Max Act: 7.9519. Min Act: -0.1700
Data Index: 8363541 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7644. Min Range: -8.7644
Max Act: 7.9519. Min Act: -0.1700
Data Index: 2541270 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7644. Min Range: -8.7644
Max Act: 7.9519. Min Act: -0.1700
Data Index: 2720775 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7644. Min Range: -8.7644
Max Act: 7.9207. Min Act: -0.1700
Data Index: 6911383 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7644. Min Range: -8.7644
Max Act: 7.9519. Min Act: -0.1700
Data Index: 8199884 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7644. Min Range: -8.7644
Max Act: 7.9519. Min Act: -0.1700
Data Index: 3497068 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7644. Min Range: -8.7644
Max Act: 7.9207. Min Act: -0.1700
Data Index: 1457405 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7644. Min Range: -8.7644
Max Act: 7.9207. Min Act: -0.1700
Data Index: 557551 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7644. Min Range: -8.7644
Max Act: 7.8894. Min Act: -0.1700
Data Index: 2011678 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #19